Byzantine Fault Research Articles

Almost-surely terminating asynchronous Byzantine agreement against general adversaries with optimal resilience

In this work, we study almost-surely terminating asynchronous Byzantine agreement (ABA) for n parties tolerating a computationally-unbounded adversary. While the existing works in this domain have primarily considered a threshold adversarial model where the adversary can corrupt any subset of up to t parties, very little attention has been paid to the non-threshold adversarial model. In the latter model, the corruption capacity of the adversary is characterized by an adversary structure Z, which enumerates all possible subsets of potentially corrupt parties and where the adversary can select any one subset from Z for corruption. While the optimal resilience for ABA against threshold adversaries is t<n/3, against non-threshold adversaries one can design an ABA protocol, provided Z satisfies the Q(3) condition; i.e. if the union of no three subsets from Z covers all the n parties. We present the first almost-surely terminating ABA protocol against Q(3) adversary structures. Previously, almost-surely terminating ABA protocol is known with non-optimal resilience where Z satisfies the Q(4) condition; i.e. if the union of no four subsets from Z covers all the n parties. To design our protocol, we present a shunning asynchronous verifiable secret-sharing (SAVSS) scheme for Q(3) adversary structures, which is of independent interest.

An Efficient and Reliable Byzantine Fault Tolerant Blockchain Consensus Protocol for Single-Hop Wireless Networks

An Efficient and Reliable Byzantine Fault Tolerant Blockchain Consensus Protocol for Single-Hop Wireless Networks

Communication-Efficient and Resilient Distributed Q-Learning.

This article investigates the problem of communication-efficient and resilient multiagent reinforcement learning (MARL). Specifically, we consider a setting where a set of agents are interconnected over a given network, and can only exchange information with their neighbors. Each agent observes a common Markov Decision Process and has a local cost which is a function of the current system state and the applied control action. The goal of MARL is for all agents to learn a policy that optimizes the infinite horizon discounted average of all their costs. Within this general setting, we consider two extensions to existing MARL algorithms. First, we provide an event-triggered learning rule where agents only exchange information with their neighbors if a certain triggering condition is satisfied. We show that this enables learning while reducing the amount of communication. Next, we consider the scenario where some of the agents can be adversarial (as captured by the Byzantine attack model), and arbitrarily deviate from the prescribed learning algorithm. We establish a fundamental trade-off between optimality and resilience when Byzantine agents are present. We then create a resilient algorithm and show almost sure convergence of all reliable agents' value functions to the neighborhood of the optimal value function of all reliable agents, under certain conditions on the network topology. When the optimal Q -values are sufficiently separated for different actions, we show that all reliable agents can learn the optimal policy under our algorithm.

A Federated Byzantine Agreement Model to Operate Offline Electric Vehicle Supply Equipment

A Federated Byzantine Agreement Model to Operate Offline Electric Vehicle Supply Equipment

Blizzard: A Distributed Consensus Protocol for Mobile Devices

We present Blizzard, a Byzantine fault tolerant (BFT) distributed ledger protocol that is aimed at making mobile devices first-class citizens in the consensus process. Blizzard introduces a novel two-tier architecture by having the mobile nodes communicate through online brokers, and includes a decentralized matching scheme to ensure each node connects to a certain number of random brokers. Through mathematical analysis, we derive a guaranteed safety region (i.e., the set of ratios of malicious nodes and malicious brokers for which the safety is assured) for the Blizzard protocol. Liveness is shown as well. We analyze the performance of Blizzard in terms of its throughput, latency, and message complexity. Through experiments based on a software implementation, we show that Blizzard is capable of throughput on the order of several thousand transactions per second per shard and sub-second confirmation latency.

Mean-square exponential convergence for Byzantine-resilient distributed state estimation

This paper studies the problem of distributed resilient state estimation (RSE) for linear measurement models in the presence of locally-bounded Byzantine nodes that may arbitrarily deviate from the prescribed update rule. Necessary and sufficient conditions for the existence of a distributed algorithm to solve the RSE problem in the almost sure sense are characterized in term of the topology-associated robustly collective observability. Under these conditions, a distributed projected stochastic resilient filtering algorithm is proposed. Compared with the existing results where asymptotic or probabilistic finite-time analysis is established, the exponential convergence (in sense of mean square) of the proposed algorithm is proved. To further improve computational performance of the algorithm, an adaptive event-triggered mechanism is constructed without compromising its correctness of the estimate.

Optimizing Blockchain Consensus: Incorporating Trust Value in the Practical Byzantine Fault Tolerance Algorithm with Boneh-Lynn-Shacham Aggregate Signature

The consensus algorithm is the core mechanism of blockchain and is used to ensure data consistency among blockchain nodes. The PBFT consensus algorithm is widely used in alliance chains because it is resistant to Byzantine errors. However, the present PBFT (Practical Byzantine Fault Tolerance) still has issues with master node selection that is random and complicated communication. The IBFT consensus technique, which is enhanced, is proposed in this study and is based on node trust value and BLS (Boneh-Lynn-Shacham) aggregate signature. In IBFT, multi-level indicators are used to calculate the trust value of each node, and some nodes are selected to take part in network consensus as a result of this calculation. The master node is chosen from among them based on which node has the highest trust value, it transforms the BLS signature process into the information interaction process between nodes. Consequently, communication complexity is reduced, and node-to-node information exchange remains secure. The simulation experiment findings demonstrate that the IBFT consensus method enhances transaction throughput rate by 61% and reduces latency by 13% when compared to the PBFT algorithm.

E-voting system using cloud-based hybrid blockchain technology

With the invention of Internet-enabled devices, cloud and blockchain-based technologies, an online voting system can smoothly carry out election processes. During pandemic situations, citizens tend to develop panic about mass gatherings, which may influence the decrease in the number of votes. This urges a reliable, flexible, transparent, secure, and cost-effective voting system. The proposed online voting system using cloud-based hybrid blockchain technology eradicates the flaws that persist in the existing voting system, and it is carried out in three phases: the registration phase, vote casting phase and vote counting phase. A timestamp-based authentication protocol with digital signature validates voters and candidates during the registration and vote casting phases. Using smart contracts, third-party interventions are eliminated, and the transactions are secured in the blockchain network. Finally, to provide accurate voting results, the practical Byzantine fault tolerance (PBFT) consensus mechanism is adopted to ensure that the vote has not been modified or corrupted. Hence, the overall performance of the proposed system is significantly better than that of the existing system. Further performance was analyzed based on authentication delay, vote alteration, response time, and latency.

Trustworthy Distributed AI Systems: Robustness, Privacy, and Governance

Emerging Distributed AI systems are revolutionizing big data computing and data processing capabilities with growing economic and societal impact. However, recent studies have identified new attack surfaces and risks caused by security, privacy, and fairness issues in AI systems. In this paper, we review representative techniques, algorithms, and theoretical foundations for trustworthy distributed AI through robustness guarantee, privacy protection, and fairness awareness in distributed learning. We first provide a brief overview of alternative architectures for distributed learning, discuss inherent vulnerabilities for security, privacy, and fairness of AI algorithms in distributed learning, and analyze why these problems are present in distributed learning regardless of specific architectures. Then we provide a unique taxonomy of countermeasures for trustworthy distributed AI, covering (1) robustness to evasion attacks and irregular queries at inference, and robustness to poisoning attacks, Byzantine attacks, and irregular data distribution during training; (2) privacy protection during distributed learning and model inference at deployment; and (3) AI fairness and governance with respect to both data and models. We conclude with a discussion on open challenges and future research directions toward trustworthy distributed AI, such as the need for trustworthy AI policy guidelines, the AI responsibility-utility co-design, and incentives and compliance.

PPBRFL: Privacy-Preserving Byzantine-Robust Federated Learning

Federated learning is a distributed machine learning approach that allows the neural network to be trained without exposing private user data. Despite its advantages, federated learning schemes still face two critical security challenges: user privacy disclosure and Byzantine robustness. The adversary may try to infer the private data from the trained local gradients or compromise the global model update. To tackle the above challenges, we propose PPBRFL, a privacy-preserving Byzantine-robust federated learning scheme. To resist Byzantine attacks, we design a novel Byzantine-robust aggregation method based on&#x0D; cosine similarity, which can guarantee the global model update and improve the model’s classification accuracy. Furthermore, we introduce a reward and penalty mechanism that considers users’ behavior to mitigate the impact of Byzantine users on the global model. To protect user privacy, we utilize symmetric homomorphic encryption to encrypt the users’ trained local models, which requires low computation cost while maintaining model accuracy. We conduct the experimental assessment of the performance of PPBRFL. The experimental results show that PPBRFL maintains model classification accuracy while ensuring privacy preservation and Byzantine robustness compared to traditional federated learning scheme.

Observer‐based finite‐time security fault‐tolerant control for nonlinear multi‐agent systems under byzantine adversaries

AbstractThis article investigates the issue of security‐based adaptive output feedback finite‐time fault‐tolerant control (FTC) for nonlinear multi‐agent systems subjected to Byzantine attacks. In this work, the fuzzy logic systems are employed to approximate the unknown nonlinearities, and unmeasurable states are estimated by the designed state observer. In addition, a data selector is designed to detect extremely malicious data of the controlled system. Considering the actuator faults, a novel Nussbaum function is utilized to compensate for the uncertainties of attacks and intermittent failures. Then, by introducing first‐order filter, an observer‐based distributed adaptive output feedback finite‐time security FTC algorithm is developed, which demonstrates all signals of the system are bounded, and the feasibility and effectiveness of the developed control scheme can be verified by simulation results.

Reaching Consensus in the Byzantine Empire: A Comprehensive Review of BFT Consensus Algorithms

Byzantine fault-tolerant (BFT) consensus algorithms are at the core of providing safety and liveness guarantees for distributed systems that must operate in the presence of arbitrary failures. Recently, numerous new BFT algorithms have been proposed, not least due to the traction blockchain technologies have garnered in the search for consensus solutions that offer high throughput, low latency, and robust system designs. In this article, we conduct a systematic survey of selected and distinguished BFT algorithms that have received extensive attention in academia and industry alike. We perform a qualitative comparison among all algorithms we review considering message and time complexities. Furthermore, we provide a comprehensive, step-by-step description of each surveyed algorithm by decomposing them into constituent subprotocols with intuitive figures to illustrate the message-passing pattern. We also elaborate on the strengths and weaknesses of each algorithm compared to the other state-of-the-art approaches.

RFVIR: A robust federated algorithm defending against Byzantine attacks

Federated learning (FL) is susceptible to Byzantine attacks due to its inherently distributed and privacy-preserving nature. Most model parameters-based defense methods become utterly ineffective under intense non-independent and identically distributed (Non-IID) scenarios. In this paper, we shift our focus from model’s parameters to the specific behavior of the model on a dataset, and propose a robust algorithm named RFVIR to defend against Byzantine attack under FL setting. RFVIR primarily tests the feature representations of each local model on a virtual dataset, and then computes the gram feature matrix to capture the difference between Byzantine attackers and benign clients, and removes suspicious local models based on Median Absolute Deviation (MAD), and finally leverage clipping operation to further mitigate the effect of potential Byzantine attackers. Since RFVIR focuses on the specific behavior of the model rather than the model parameters, it applies to intense Non-IID scenarios. We conduct experiments on CIFAR-10, MNIST, and GTSRB datasets, considering five typical Byzantine attacks and various attack scenarios. The experimental results demonstrate that RFVIR can successfully defend against various Byzantine attacks and outperform the existing robust algorithms.

FedSuper: A Byzantine-Robust Federated Learning Under Supervision

Federated Learning (FL) is a machine learning setting where multiple worker devices collaboratively train a model under the orchestration of a central server, while keeping the training data local. However, owing to the lack of supervision on worker devices, FL is vulnerable to Byzantine attacks where the worker devices controlled by an adversary arbitrarily generate poisoned local models and send to FL server, ultimately degrading the utility (e.g., model accuracy) of the global model. Most of existing Byzantine-robust algorithms, however, cannot well react to the threatening Byzantine attacks when the ratio of compromised worker devices (i.e., Byzantine ratio) is over 0.5 and worker devices’ local training datasets are not independent and identically distributed (non-IID). We propose a novel Byzantine-robust Fed erated Learning under Super vision (FedSuper), which can maintain robustness against Byzantine attacks even in the threatening scenario with a very high Byzantine ratio (0.9 in our experiments) and the largest level of non-IID data (1.0 in our experiments) when the state-of-the-art Byzantine attacks are conducted. The main idea of FedSuper is that the FL server supervises worker devices via injecting a shadow dataset into their local training processes. Moreover, according to the local models’ accuracies or losses on the shadow dataset, we design a Local Model Filter to remove poisoned local models and output an optimal global model. Extensive experimental results on three real-world datasets demonstrate the effectiveness and the superior performance of FedSuper, compared to five latest Byzantine-robust FL algorithms and two baselines, in defending against two state-of-the-art Byzantine attacks with high Byzantine ratios and high levels of non-IID data.

VSSB-Raft: A Secure and Efficient Zero Trust Consensus Algorithm for Blockchain

To solve the problems of vote forgery and malicious election of candidate nodes in the Raft consensus algorithm, we combine zero trust with the Raft consensus algorithm and propose a secure and efficient consensus algorithm -Verifiable Secret Sharing Byzantine Fault Tolerance Raft Consensus Algorithm (VSSB-Raft). The VSSB-Raft consensus algorithm realizes zero trust through the supervisor node and secret sharing algorithm without the invisible trust between nodes required by the algorithm. Meanwhile, the VSSB-Raft consensus algorithm uses the SM2 signature algorithm to realize the characteristics of zero trust requiring authentication before data use. In addition, by introducing the NDN network, we redesign the communication between nodes and guarantee the communication quality among nodes. The VSSB-Raft consensus algorithm proposed in this paper can make the algorithm Byzantine fault tolerant by setting a threshold for secret sharing while maintaining the algorithm’s complexity to be O(n). Experiments show that the VSSB-Raft consensus algorithm is secure and efficient with high throughput and low consensus latency.

An AI-enabled secure framework for enhanced elder healthcare

The healthcare sector has been revolutionized by Information and Communication Technology (ICT), leading to increased patient life expectancy and reduced healthcare costs. In the realm of cutting-edge research, Digital Twins (DT) technology holds great promise for improving healthcare. This study introduces a new approach to securing adult healthcare data by combining the Internet of Things (IoT), DT technology, and blockchain technology. Specifically, a context-aware physical activity monitoring framework is proposed for adult healthcare, incorporating an Artificial Intelligence-inspired Convolutional Neural Network (CNN) technique to analyze real-time abnormalities in the elderly. The CNN is trained on a large dataset, learning to recognize patterns and anomalies associated with abnormal conditions or behaviors in the elderly. The framework also ensures data security through the advanced features of blockchain, employing the Reputation-based Byzantine Fault Tolerance (RBFT) method for the consortium network. Experimental simulations validate the proposed technique, demonstrating its superior efficacy compared to state-of-the-art techniques. The results exhibit betters statistical measures of Delay Latency (121.23s), Prediction Efficacy (Precision (93.357%), Specificity (93.58%), Sensitivity (94.15%), and F-measure (94.58%)), Reliability (89.62%), and Stability (71%).

Asynchronous Robust Aggregation Method with Privacy Protection for IoV Federated Learning

Due to the wide connection range and open communication environment of internet of vehicle (IoV) devices, they are susceptible to Byzantine attacks and privacy inference attacks, resulting in security and privacy issues in IoV federated learning. Therefore, there is an urgent need to study IoV federated learning methods with privacy protection. However, the heterogeneity and resource limitations of IoV devices pose significant challenges to the aggregation of federated learning model parameters. Therefore, this paper proposes an asynchronous robust aggregation method with privacy protection for federated learning in IoVs. Firstly, we design an asynchronous grouping robust aggregation algorithm based on delay perception, combines intra-group truth estimation with inter-group delay aggregation, and alleviates the impact of stragglers and Byzantine attackers. Then, we design a communication-efficient and security enhanced aggregation protocol based on homomorphic encryption, to achieve asynchronous group robust aggregation while protecting data privacy and reducing communication overhead. Finally, the simulation results indicate that the proposed scheme could achieve a maximum improvement of 41.6% in model accuracy compared to the baseline, which effectively enhances the training efficiency of the model while providing resistance to Byzantine attacks and privacy inference attacks.

Robust Reward-Free Actor-Critic for Cooperative Multiagent Reinforcement Learning.

In this article, we consider centralized training and decentralized execution (CTDE) with diverse and private reward functions in cooperative multiagent reinforcement learning (MARL). The main challenge is that an unknown number of agents, whose identities are also unknown, can deliberately generate malicious messages and transmit them to the central controller. We term these malicious actions as Byzantine attacks. First, without Byzantine attacks, we propose a reward-free deep deterministic policy gradient (RF-DDPG) algorithm, in which gradients of agents' critics rather than rewards are sent to the central controller for preserving privacy. Second, to cope with Byzantine attacks, we develop a robust extension of RF-DDPG termed R2F-DDPG, which replaces the vulnerable average aggregation rule with robust ones. We propose a novel class of RL-specific Byzantine attacks that fail conventional robust aggregation rules, motivating the projection-boosted robust aggregation rules for R2F-DDPG. Numerical experiments show that RF-DDPG successfully trains agents to work cooperatively and that R2F-DDPG demonstrates robustness to Byzantine attacks.

An Experimental Study of Byzantine-Robust Aggregation Schemes in Federated Learning

Byzantine-robust federated learning aims at mitigating Byzantine failures during the federated training process, where malicious participants may upload arbitrary local updates to the central server to degrade the performance of the global model. In recent years, several robust aggregation schemes have been proposed to defend against malicious updates from Byzantine clients and improve the robustness of federated learning. These solutions were claimed to be Byzantine-robust, under certain assumptions. Other than that, new attack strategies are emerging, striving to circumvent the defense schemes. However, there is a lack of systematic comparison and empirical study thereof. In this paper, we conduct an experimental study of Byzantine-robust aggregation schemes under different attacks using two popular algorithms in federated learning, FedSGD and FedAvg . We first survey existing Byzantine attack strategies and Byzantine-robust aggregation schemes that aim to defend against Byzantine attacks. We also propose a new scheme, ClippedClustering , to enhance the robustness of a clustering-based scheme by automatically clipping the updates. Then we provide an experimental evaluation of eight aggregation schemes in the scenario of five different Byzantine attacks. Our results show that these aggregation schemes sustain relatively high accuracy in some cases but are ineffective in others. In particular, our proposed ClippedClustering successfully defends against most attacks under independent and IID local datasets. However, when the local datasets are Non-IID, the performance of all the aggregation schemes significantly decreases. With Non-IID data, some of these aggregation schemes fail even in the complete absence of Byzantine clients. We conclude that the robustness of all the aggregation schemes is limited, highlighting the need for new defense strategies, in particular for Non-IID datasets.

Robust Federated Learning: Maximum Correntropy Aggregation Against Byzantine Attacks.

As an emerging decentralized machine learning technique, federated learning organizes collaborative training and preserves the privacy and security of participants. However, untrustworthy devices, typically Byzantine attackers, pose a significant challenge to federated learning since they can upload malicious parameters to corrupt the global model. To defend against such attacks, we propose a novel robust aggregation method-maximum correntropy aggregation (MCA), which applies the maximum correntropy criterion (MCC) to derive a central value from parameters. Different from the previous use of MCC for denoising, we utilize it as a similarity metric to measure parameter distribution and aggregate a robust center. Correntropy in MCC, with all even-order moments of the parameter, contains high-order statistical properties, which allows for a comprehensive capture of parameter characteristics, thus helping to prevent interference from attackers. Meanwhile, correntropy extracts information from the parameters themselves, without requiring the proportion of malicious attackers. Through the fixed-point iteration, we solve the optimization objective, demonstrating the linear convergence of the iteration formula. Theoretical analysis reveals the robustness aggregation property of MCA and the error bound between MCA and the global optimal solution, with linear convergence to the optimal solution neighborhood. By performing independent identically distribution (IID) and non-IID experiments on three different datasets, we show that MCA exhibits significant robustness under mainstream attacks, whereas other methods cannot withstand all of them.